Result of Service

Expert delivery of machine learning assigned tasks and activities in support of ICTS projects and programs.

Work Location

UN House – ESCWA

Expected duration

12 Months w/ext.

Duties and Responsibilities

Background:
In empirical economics, machine learning techniques, the usage of big data and unstructured data have become one of the most powerful technologies in the last decade to producing more accurate and timely economic forecasts and evidence-based policymaking. Several challenges remain among which carrying analysis in a data poor environment, ensuring model fitting quality over time, identifying causal relationships, and sustaining accuracy of forecasts in times of crisis but new advances are addressing these issues.
Against this backdrop, the Information Communication and Technology Section (ICTS) has established a Data Science and Computational Economics (DSCE) team bringing together a multidisciplinary team (economists, computer scientists, statisticians) with the view of developing data science models and applying advanced and novel techniques and methods (AI/ML) to monitor and understand the drivers of economic phenomenon in support of evidence-based policymaking.

Duties and Responsibilities:
Under the overall guidance of the Chief, ICTS, and direct supervision by the Unit Head, Data Science and Computational Economics Unit, the consultant will perform the following tasks:

1.Problem Definition: Work with stakeholders to clearly define the business problem and translate it into a machine learning problem. This may involve defining the objective, selecting appropriate features, and defining the target variable. The machine learning analyst should have a deep understanding of the business domain and be able to identify the most important factors affecting the target variable.

2.Data Collection: Collect and organize relevant data from various sources, such as databases, spreadsheets, and APIs. This may involve tasks such as accessing data from different systems, merging data from different sources, and cleaning the data to remove errors, inconsistencies, and outliers. The machine learning analyst should be familiar with data preparation techniques, such as data imputation, normalization, and feature scaling.

3.Data Exploration: Conduct a thorough exploratory data analysis to understand the data and identify patterns and relationships. This may involve tasks such as visualizing data using plots and charts, calculating summary statistics, and identifying correlations between variables. The machine learning analyst should be able to identify important features and patterns in the data and communicate their findings to stakeholders.
4.Model Implementation and Evaluation: Implement and evaluate various machine learning algorithms to determine the best performing models. This may involve comparing the performance of different algorithms such as linear regression, decision trees, random forests, support vector machines, k-nearest neighbors, and deep learning methods. The best model will be selected based on metrics such as accuracy, precision, recall, F1 score, and other performance metrics relevant to the specific problem at hand.

5.Hyperparameter Tuning: Tune hyperparameters of the selected models to optimize performance. This may involve using techniques such as grid search, random search, or Bayesian optimization. The objective is to find the best combination of hyperparameters that results in the highest performance on the validation set.

6.Model Deployment: Build and maintain machine learning models in production. This may involve tasks such as automating the model training and prediction processes, monitoring model performance, and updating the model as needed. The machine learning analyst should be familiar with deployment tools and frameworks, such as TensorFlow, PyTorch, or scikit-learn, and be able to deploy models in a scalable and efficient manner.

7.Results Communication: Communicate results and insights to stakeholders in a clear and concise manner. This may include visualizing results using plots, tables, and dashboards, and presenting the results to stakeholders in a way that is easy to understand. The machine learning analyst should be able to clearly explain the results, the methods used, and the implications for the business.

8.Model Monitoring and Improvement: Monitor model performance and suggest improvements as needed. This may involve tasks such as retraining the model with new data, modifying the model architecture, or incorporating new features. The machine learning analyst should be able to identify when a model is underperforming and suggest steps to improve it.

9.Stay Up-to-date: Stay up-to-date with the latest advancements in machine learning and incorporate new techniques as appropriate. This may involve attending workshops and conferences, reading research papers, and participating in online forums. The machine learning analyst should be constantly learning and expanding their knowledge in the field.

10.Technical Support: Provide technical support for data science projects. This may include tasks such as assisting with the setup of the development environment, resolving technical issues, and providing guidance on best practices for machine learning. The machine learning analyst should have strong technical skills and be able to help others with their technical needs.

11.Collaboration: Collaborate with other data science and engineering teams to implement and deploy machine learning solutions. This may involve working with data engineers to access and integrate data, working with software engineers to deploy models in production, and working with other data scientists to share knowledge and best practices. The machine learning analyst should be a strong team player and be able to effectively communicate and collaborate with others to achieve common goals.

Qualifications/special skills

A Master’s degree in a relevant field such as computer science, machine learning, artificial intelligence, statistics, or a related discipline is required. A Ph.D. is desirable.

All candidates must submit a copy of the required educational degree. Incomplete applications will not be reviewed.
A minimum of seven (7) years of experience with machine learning frameworks and libraries (e.g., TensorFlow, PyTorch, scikit-learn) is required.
Strong proficiency in programming languages commonly used in machine learning, such as Python and R is required.
Expertise in various machine learning techniques, such as supervised learning, unsupervised learning, deep learning, and reinforcement learning is required.
A minimum of five 5 years’ experience with cloud platforms (e.g., AWS, Azure, Google Cloud) and their machine learning services is required.
Proven track record of developing and deploying machine learning models for real-world applications is required.
A minimum of four (4) year’s experience with exploratory data analysis and data visualization is required.
Understanding of the ethical considerations and potential biases associated with machine learning models is desirable.
Familiarity with big data technologies (e.g., Hadoop, Spark) and distributed computing frameworks is desirable.
The below Technical Skills are desirable:
Deep understanding of statistical analysis, algorithms, and data structures.
Proficiency in using SQL and working with relational databases.
Strong software development skills and understanding of software engineering best practices.
Experience with version control systems (e.g., Git) and collaborative development workflows.
Ability to work effectively in cross-functional teams and communicate complex technical concepts to non-technical stakeholders.
Strong problem-solving and analytical thinking abilities.
The below list of expertise in Machine Learning is desirable:
Strong knowledge of feature engineering, feature selection, and dimensionality reduction techniques.
Experience with natural language processing (NLP) and text analytics.
Familiarity with computer vision and image processing algorithms.
Proficiency in data preprocessing, cleaning, and transformation techniques.
Ability to work with large datasets and perform efficient data manipulation.

Languages

English and French are the working languages of the United Nations Secretariat; and Arabic is a working language of ESCWA.

For this position, fluency in English is required.

Note: “Fluency” equals a rating of ‘fluent’ in all four areas (speak, read, write, and understand) and “Knowledge of” equals a rating of ‘confident’ in two of the four areas.

No Fee

THE UNITED NATIONS DOES NOT CHARGE A FEE AT ANY STAGE OF THE RECRUITMENT PROCESS (APPLICATION, INTERVIEW MEETING, PROCESSING, OR TRAINING). THE UNITED NATIONS DOES NOT CONCERN ITSELF WITH INFORMATION ON APPLICANTS’ BANK ACCOUNTS.